SecondSourceJudgment rebuilt from primary sources

Perplexity, the AI search company, launched Orchestrator API, one API for more than 85 models; in its own test, passing Claude Fable 5.2's refusals to an OpenAI model solved 41 of 63 tasks, against 38 for Fable 5.2 alone.

Concept illustration: a tablet lies on a beige surface above a grey pencil, its screen showing a dark teal header with a teal starburst-shaped icon and the words PERPLEXITY ORCHESTRATOR, a column of small laptop icons down the left, and two rows divided by a thin line. In each row an arrow runs from a stack of light cards to a laptop with a speech bubble on its screen labelled CLAUDE FABLE 5.2, which points right to a long grey bar; in the top row a down arrow leads from it to a tray of grey cards marked with X, while in the bottom row a red elbow arrow leads from it to a second laptop labelled OPENAI with a green knot-shaped icon, which points right to a small stack of cards and down to a tray of grey X-marked cards. Printed on the image: 41 vs 38 Tasks solved of 63, one Perplexity test: Fable 5.2 with vs without refusals sent to an OpenAI model.

Routing refusals to another vendor's model solved 41 of the 63 tasks instead of 38, but Perplexity ran the test only once, so the gap may be luck, and cost per task was higher. The tasks are a 63-task subset of Terminal-Bench 4.1. When the same model fails at one provider, Orchestrator retries with another provider (Perplexity, 2026-11-17). How we checked →

Source and checks

This item ran in the brief of Nov 18, 2026, alongside 14 other items. How we checked it, the quote checks and what was still missing that day are on that issue's How we checked page.

Cite this item

SecondSource (2026). "Perplexity, the AI search company, launched Orchestrator API, one API for more than 85 models; in its own test, passing Claude Fable 5.2's refusals to an OpenAI model solved 41 of 63 tasks, against 38 for Fable 5.2 alone.." https://secondsource.io/en/product/2026-11-18-2/. Accessed access date.